Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of battles or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to battles, particularly named battles or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATURE
    -0.71
    eus
    -0.66
    ure
    -0.65
    IJ
    -0.63
    eller
    -0.61
    ols
    -0.61
    ophile
    -0.59
    OA
    -0.59
    zzle
    -0.59
    ilk
    -0.58
    POSITIVE LOGITS
    front
    1.18
    cru
    1.16
     roy
    1.16
    axe
    1.14
    fleet
    1.10
    cry
    1.09
    mage
    1.02
     Royale
    0.98
    ments
    0.97
     raged
    0.96
    Act Density 0.039%

    No Known Activations